HealthData.gov MCP. Query public health records from HHS.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
HealthData.gov (HHS Open Data) connects your agent directly to thousands of public health records from the U.S. Department of Health & Human Services.
Use this MCP to discover datasets, run complex data queries using SoQL, and pull real-time metrics on anything from hospital capacity to Medicare utilization.
What your AI agents can do
Get catalog
Lists the names and details of thousands of datasets available within the HealthData.gov catalog.
Query dataset
Runs a specific query against a named dataset using SoQL to pull filtered or aggregated data.
Lists thousands of public health and social service datasets hosted by HHS for you to review.
Narrows down massive tables using advanced filtering parameters to extract only the relevant rows of information.
Calculates summaries, counts, and averages from selected datasets—like finding the top five states by utilization rate.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
HealthData.gov (HHS Open Data) 2 Tools
Use these tools to explore the metadata catalog, list available HHS datasets, or run complex queries against specific public health records.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using HealthData.gov (HHS Open Data) on Vinkius019e38a7get catalog
Lists the names and details of thousands of datasets available within the HealthData.gov catalog.
019e38a7query dataset
Runs a specific query against a named dataset using SoQL to pull filtered or aggregated data.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with HealthData.gov (HHS Open Data), then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by HealthData.gov. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 2 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Getting Health Data Used To Be a Paper Trail Nightmare
Before this, getting reliable data meant clicking through multiple government websites. You'd find one state's hospital capacity on site A, and Medicare utilization stats on portal B. Then you had to manually download dozens of CSV files, rename the columns so they matched up, and spend hours cross-referencing dates just to get a single coherent picture.
Now, your agent handles that mess. You tell it what data points you need—say, 'Show me ICU rates for three states over six months.' The MCP writes the complex queries behind the scenes, pulls all the disparate records together, and presents the clean analysis right in your chat window.
The power of HealthData.gov (HHS Open Data)
You don't have to worry about which dataset ID is current or what complex SoQL syntax you need to remember. The system guides your agent, letting it first run `get_catalog` to surface the right data options for you.
What changes now is that you move from being a data collector to a data analyst. You focus on asking smart questions; the MCP handles the messy work of connecting and querying the source material.
What you can do with this MCP connector
This connector lets your AI client access massive amounts of open government data from HHS. Instead of navigating confusing state portals or downloading huge CSV files, you tell your agent what you need—say, 'What's the current ICU rate in Texas?' Your agent handles finding the right dataset and writing the query code automatically.
You can list every available resource to see what exists, then focus on filtering and sorting down to just the records you need. This means data scientists or public health officials can get deep insights without ever touching a complex database interface. It's like having an analyst sitting next to your AI client, ready to pull precise figures from any corner of government data, all managed through Vinkius.
019e38a7-5ccd-7298-9c11-6cd6d9f227ca 
How HealthData.gov MCP Works
- 1 Subscribe to this MCP. (If needed, enter your HealthData.gov App Token for higher limits.)
- 2 Your agent uses the catalog tool to search and list relevant datasets based on a topic or ID.
- 3 You prompt your agent to query the specific dataset using criteria like sorting or filtering parameters.
The bottom line is that you use natural language conversation instead of complex database commands to get structured data answers.
Who Is HealthData.gov MCP For?
This MCP is for the Public Health Official who needs live, state-by-state metrics; the Data Scientist needing to prototype queries fast; or the Researcher tracking long-term trends across multiple datasets.
Monitors live data streams and public health trends across different states or regions, quickly checking for spikes in hospitalizations.
Tests complex data queries to prototype new analytics models using official HHS datasets without needing direct API access.
Retrieves subsets of Medicare/Medicaid data for academic papers, focusing on specific demographics or time periods.
What Changes When You Connect
- Stop downloading massive files. By using the
query_datasettool, you filter and sort data in real-time, getting only the specific records you need—no gigabytes of junk data to sift through. - You don't have to remember complex IDs. Use the
get_catalogtool first. It lets your agent search and list datasets by topic, making discovery straightforward for anyone. - Analyze diverse public metrics in one conversation. You can track everything from COVID-19 stats to provider directories using a single interface, eliminating switching between different government websites.
- Speed up research prototyping. Data scientists use this MCP to test complex SoQL queries immediately within your agent's chat window, speeding up the development cycle significantly.
- Access Medicare/Medicaid data easily. This connector gives you direct access to critical health service utilization records that are usually locked behind developer portals.
Real-World Use Cases
Tracking state-level ICU capacity changes
A public health official needs to know which states reported the highest adult ICU utilization last month. They ask their agent, and it uses query_dataset with sorting parameters to pull a ranked list of the top 5 states immediately.
Finding datasets about community wellness
A researcher needs data on nutrition surveys but isn't sure which dataset name to use. They ask their agent to run get_catalog first, which lists relevant options like 'National Health Nutrition Examination Survey,' allowing the researcher to select it.
Comparing multiple health metrics
A developer wants to build a dashboard comparing provider utilization and Medicare costs. They use their agent to query two different datasets sequentially, compiling both data sets into one analysis for immediate review.
The Tradeoffs
Jumping straight to the query
The user tries to run a complex query_dataset call without knowing if the dataset ID is correct or if it's updated. This fails, leaving them stuck and wasting time.
→
Always start by asking your agent to use the get_catalog tool first. Use that list to confirm the exact name of the dataset before you attempt any query with query_dataset.
Over-downloading data
The user asks for all records on a topic, causing the agent to pull down millions of rows into a massive file that is impossible to read or analyze.
→
Be specific. Use query_dataset and tell your agent exactly what parameters to use—like filtering by date range or selecting only 'State' and 'Count' fields.
Using the tool for general knowledge
The user asks, 'What are the best practices in public health?' The agent can't answer this; it only works with data.
→ Keep your requests focused on verifiable metrics. Only ask questions that require retrieving or calculating values from a specific HHS dataset.
When It Fits, When It Doesn't
Use this MCP if your job requires accessing structured, real-world public health statistics (e.g., hospital rates, Medicare spending). The key is data retrieval, not general research. Don't use it if you need to write an essay or summarize policy changes—you'll get the raw numbers. If you just need a list of available datasets, start with get_catalog. If you know the dataset and what metrics you want (like 'top 5 states by utilization'), then proceed directly to query_dataset after confirming the ID.
Common Questions About HealthData.gov MCP
How do I find a specific dataset about 'Medicare'? +
Use the get_catalog tool and provide 'Medicare' in the q parameter. This will return a list of relevant datasets along with their unique identifiers (dataset_id).
Can I filter results to only show data from a specific state? +
Yes! When using query_dataset, use the $where parameter with a SoQL filter like state='NY'. You can also use $select to pick specific columns.
Is an API key required to access this data? +
No, the data is public. However, providing a HEALTHDATA_APP_TOKEN is recommended for higher rate limits if you plan to perform many queries.
What happens if my queries exceed the default rate limit when I use `query_dataset`? +
The system will return a rate-limiting error. To handle high volumes, you should enter your HealthData.gov/Socrata App Token in the setup options. This token increases your query capacity and helps maintain stable data retrieval.
Does running `get_catalog` show every single dataset published by the HHS? +
No, it provides access to the main catalog of datasets managed via HealthData.gov. While this is a massive collection, certain specialized or internal departmental data may exist outside of the scope shown here.
If I get an error when using `query_dataset`, how can I debug my SoQL syntax? +
Check your specific dataset's documentation for precise usage examples. You must ensure that all field names and parameters used in the query exactly match what is available in the target data source.
When I use `query_dataset`, what format does the returned public health data take? +
The tool returns structured, machine-readable data—typically JSON. This format makes it easy for your AI client to parse and analyze the metrics immediately within the conversation.
Can I use the information from `get_catalog` in an application outside of Vinkius or my AI agent? +
The MCP is designed specifically for integration with your AI agent. While the underlying data is public, you must connect through a compatible client to execute the catalog retrieval tools.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.